| dc.description.abstract | The emergence of COVID-19 as a global health crisis has necessitated the development of effective detection strategies to combat its spread. The ability to identify infections at an early stage is vital for the timely treatment and recovery of affected individuals. In response to this need, the scientific community has been exploring various methods for diagnosing the virus, including cutting-edge software and deep learning techniques. Among these, the use of advanced deep learning models, such as those integrating Keras's ResNet50V2 and ResNet152V2, has shown promise in enhancing early detection efforts.
Building on this foundation, our research introduces an innovative Convolutional Neural Network (CNN) model specifically designed for the automatic detection of COVID-19 through chest X-ray images. The focus of our study is to conduct a comprehensive comparison between this novel CNN model and traditional deep learning approaches in the context of COVID-19 diagnosis. The results of our investigation are highly encouraging, with our model achieving an exceptional accuracy rate of 99.97% and a precision rate of 99.99%. These findings underscore the significant potential of our model to be integrated into clinical workflows, offering a powerful tool for healthcare professionals in the fight against COVID-19. Through this work, we aim to contribute to the ongoing efforts to improve public health outcomes during this challenging time. | en_US |
